Papers › ART: Anonymous Region Transformer for Variable Multi-Layer Transparent Image Generation

ART: Anonymous Region Transformer for Variable Multi-Layer Transparent Image Generation

25 Feb 2025CVPR 2025 1arXiv:2502.18364archive 2025-07-28

Yifan Pu, Yiming Zhao, Zhicong Tang, Ruihong Yin, Haoxing Ye, Yuhui Yuan, Dong Chen, Jianmin Bao, Sirui Zhang, Yanbin Wang, Lin Liang, Lijuan Wang, Ji Li, Xiu Li, Zhouhui Lian, Gao Huang, Baining Guo

Multi-layer image generation is a fundamental task that enables users to isolate, select, and edit specific image layers, thereby revolutionizing interactions with generative models. In this paper, we introduce the Anonymous Region Transformer (ART), which facilitates the direct generation of variable multi-layer transparent images based on a global text prompt and an anonymous region layout. Inspired by Schema theory suggests that knowledge is organized in frameworks (schemas) that enable people to interpret and learn from new information by linking it to prior knowledge.}, this anonymous region layout allows the generative model to autonomously determine which set of visual tokens should align with which text tokens, which is in contrast to the previously dominant semantic layout for the image generation task. In addition, the layer-wise region crop mechanism, which only selects the visual tokens belonging to each anonymous region, significantly reduces attention computation costs and enables the efficient generation of images with numerous distinct layers (e.g., 50+). When compared to the full attention approach, our method is over 12 times faster and exhibits fewer layer conflicts. Furthermore, we propose a high-quality multi-layer transparent image autoencoder that supports the direct encoding and decoding of the transparency of variable multi-layer images in a joint manner. By enabling precise control and scalable layer generation, ART establishes a new paradigm for interactive content creation.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 14 code samples harvested from 1 repository linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 14 samples from 1 repository, 13 ran (12 with no instrument failure; 1 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

microsoft/art-msra mentioned on GitHubpytorchMITSyntology: 14 samples, 13 ran (1 instrument-failed) · 1 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

14 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran; the contract check could not run
12ran
1unverified

Licence: 0 of the 14 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from microsoft/art-msra. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

microsoft/art-msra community (archive-listed) 14 samples, 13 ran (1 instrument-failed) · 1 unverified
FormulateInput layout_planner/inference_layout.py ran fingerprinted MIT (permissive) · 07f3e48fb520f32b · report fixture: signature intention:str/0/str · returned dict · level recorded 2026-09-25
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
layout_planner/training/utils.py ran; the contract check could not run (RAISES) MIT (permissive) · ed5ed903e9e24d08 · report fixture: signature output:Tensor/2/float, target:Tensor/1/int, padding:int/0/int, topk:tuple/1/int · returned list · level recorded 2026-09-22
batch_purity layout_planner/training/trainer_layout.py ran MIT (permissive) · b6ae4c2e9a4721f3 · report fixture: signature input_ids:Tensor/2/int, tokenizer:MockTokenizer/0/? · returned list · level recorded 2026-09-24
crop_each_layer multi_layer_gen/custom_model_transp_vae.py ran MIT (permissive) · 28e0f66d8fa6cea8 · report fixture: signature hidden_states:Tensor/4/float, use_layers:list/1/int, list_layer_box:list/1/tuple, H:int/0/int, W:int/0/int, pos_embedding:callable/0/? · returned tuple · level recorded 2026-09-24
encode_prompt in 54 papers multi_layer_gen/custom_pipeline.py ran MIT (permissive) · 06d07c5e65ea4167 · report fixture: signature tokenizers:tuple/1/callable, text_encoders:tuple/1/callable, prompt:list/1/str, prompt_2:list/1/str, num_images_per_prompt:int/0/int, max_sequence_length:int/0/int · returned tuple · level recorded 2026-09-24
get_quantizer layout_planner/training/datasets/quantizer.py ran MIT (permissive) · c345a9eaf4ac73c4 · report fixture: signature version:str/0/str, quant:bool/0/bool, simplify_json:bool/0/bool, width:int/0/int, height:int/0/int · returned QuantizerV4 · level recorded 2026-09-24
kmp_preprocess layout_planner/models/modeling_layout.py ran fingerprinted MIT (permissive) · 00462e6910b34cb9 · report fixture: signature pattern:list/1/int · returned list · level recorded 2026-09-25
kmp_search layout_planner/models/modeling_layout.py ran MIT (permissive) · f150a306a653ecb2 · report fixture: signature text:list/1/str, pattern:list/1/str · returned list · level recorded 2026-09-25
l2_loss in 136 papers layout_planner/training/trainer_layout.py ran fingerprinted MIT (permissive) · 61490145cb48f028 · report fixture: signature u:Tensor/3/float, v:Tensor/3/float · returned Tensor · level recorded 2026-09-24
layout_collate_fn layout_planner/training/datasets/layoutnew_dataset.py ran MIT (permissive) · f4d9f77d7e39090d · report fixture: signature batch:list/1/dict · returned dict · level recorded 2026-09-24
patchify in 32 papers
census: 6 implementations from 8 papers, 6 distinct outputs across 3 buckets, one shared input per bucket
multi_layer_gen/custom_model_transp_vae.py ran fingerprinted MIT (permissive) · 91a80a2215fe15e4 · report fixture: signature x:Tensor/4/float, patch_size:int/0/int · returned Tensor · level recorded 2026-09-24
preprocess_Input layout_planner/inference_layout.py ran fingerprinted MIT (permissive) · d6905e2f00e0a901 · report fixture: signature intention:str/0/str · returned str · level recorded 2026-09-24
unpatchify in 18 papers multi_layer_gen/custom_model_transp_vae.py ran fingerprinted MIT (permissive) · 74720e4c7d36e702 · report fixture: signature x:Tensor/4/float, patch_size:int/0/int · returned Tensor · level recorded 2026-09-24
get_dataset in 285 papers layout_planner/training/datasets/layoutnew_dataset.py unverified MIT (permissive) · 7a4f7b082e40ac6b · report

Tasks

Image Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ALIGNAbsolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSETSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections